A PyTorch implementation of Connected Components Labeling

[CVPR2024 Highlight]GLEE: General Object Foundation Model for Images and Videos at Scale

Modern WebSocket support for Flask.

Monocular Depth Estimation Toolbox based on MMSegmentation.

Pipeline Parallelism for PyTorch

Kernl lets you run PyTorch transformer models several times faster on GPU with a single line of code, and is designed to be easily hackable.

Model parallel transformers in JAX and Haiku

Flax is a neural network library for JAX that is designed for flexibility.

JAX-based neural network library

Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.

Pax is a Jax-based machine learning framework for training large scale models. Pax allows for advanced and fully configurable experimentation and parallelization, and has demonstrated industry lead…

2nd solution of ICDAR 2021 Competition on Scientific Literature Parsing, Task B.

Making large AI models cheaper, faster and more accessible

JAX - A curated list of resources https://github.com/google/jax

Abseil Common Libraries (Python)

Abseil Common Libraries (C++)

ConvMAE: Masked Convolution Meets Masked Autoencoders

A paper list of some recent Transformer-based CV works.

torch-optimizer -- collection of optimizers for Pytorch

Enabling PyTorch on XLA Devices (e.g. Google TPU)

Scalable PaLM implementation of PyTorch

TorchMultimodal is a PyTorch library for training state-of-the-art multimodal multi-task models at scale.

Code & Models for 3DETR - an End-to-end transformer model for 3D object detection

functorch is JAX-like composable function transforms for PyTorch.

The friendly PIL fork

PyTorch implementation of MAE https//arxiv.org/abs/2111.06377

Ongoing research training transformer models at scale

Dense Contrastive Learning (DenseCL) for self-supervised representation learning, CVPR 2021 Oral.